WO2016047683A1 - Medical image display processing method, medical image display processing device, and program - Google Patents

Medical image display processing method, medical image display processing device, and program Download PDF

Info

Publication number
WO2016047683A1
WO2016047683A1 PCT/JP2015/076918 JP2015076918W WO2016047683A1 WO 2016047683 A1 WO2016047683 A1 WO 2016047683A1 JP 2015076918 W JP2015076918 W JP 2015076918W WO 2016047683 A1 WO2016047683 A1 WO 2016047683A1
Authority
WO
WIPO (PCT)
Prior art keywords
atrophy
brain
degree
image
disease
Prior art date
Application number
PCT/JP2015/076918
Other languages
French (fr)
Japanese (ja)
Inventor
小野　徹太郎
智章 後藤
博史 松田
Original Assignee
大日本印刷株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 大日本印刷株式会社 filed Critical 大日本印刷株式会社
Priority to CN201580047080.9A priority Critical patent/CN106659424B/en
Priority to ES15845121T priority patent/ES2857099T3/en
Priority to US15/504,774 priority patent/US10285657B2/en
Priority to EP15845121.1A priority patent/EP3199102B1/en
Publication of WO2016047683A1 publication Critical patent/WO2016047683A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves 
    • A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves  involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
    • A61B6/501—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of the head, e.g. neuroimaging or craniography
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Definitions

  • the present invention relates to a diagnosis support technology that supports diagnosis of a brain disease based on a brain image captured by MRI or the like, and more particularly to a technology that performs diagnosis support that is suitable when a plurality of diseases are assumed.
  • SPECT Single Photon Emission Computed Tomography
  • PET PET
  • CT Computerized Tomography
  • MRI Magnetic Resonance Imaging
  • Patent Document 1 discloses a system for assisting diagnosis of Alzheimer's disease, and diagnostically assessing Alzheimer's disease by quantitatively evaluating atrophy of the medial temporal region using an MRI image. It is possible to do
  • the present invention has been made in view of the above-described problems, and an object thereof is to provide a diagnosis support device and the like suitable for comparison of different diseases.
  • a specifying means for specifying a region of the brain associated with a plurality of diseases from a brain image, and a comparison display means for calculating and comparing and displaying information concerning the specified region. It is a diagnosis support device characterized by having. According to the first invention, a diagnostic support device suitable for comparing different diseases is provided.
  • the comparison display means preferably displays the distribution of the atrophy score together with the site on the brain image. Since the distribution of the atrophy score is displayed on the brain image together with the region related to each disease by this, it is possible to visually grasp the atrophy of the whole brain image and the atrophy of the region of interest.
  • the comparison display means calculate and display the atrophy degree indicating the degree of atrophy at the site from the atrophy score. By this, it is possible to quantitatively compare atrophy of the site associated with each disease.
  • the comparison display means preferably displays the degree of atrophy for each tissue. This makes it possible to quantitatively compare atrophy of the site associated with each disease for each tissue.
  • the comparison display means preferably calculates and displays atrophy ratio which is a ratio of the atrophy degree of each part. This provides an effective indicator for discrimination support that can uniquely identify the relationship between different diseases.
  • the calculation means calculate the atrophy score by comparing the brain image with a normal person's brain image. Thereby, the atrophy score is calculated by comparison with the healthy person image.
  • the site is preferably a site of the brain where the difference in atrophy appears between Alzheimer's dementia and Lewy body dementia. This realizes diagnostic support suitable for comparing Alzheimer's dementia and Lewy body dementia.
  • the site is preferably near the medial temporal region and near the posterior brainstem. This realizes diagnostic support suitable for comparing Alzheimer's dementia and Lewy body dementia.
  • the second invention for achieving the above-mentioned object comprises a specifying step of specifying a region of the brain associated with a plurality of diseases from a brain image, and a comparison display step of calculating and comparing and displaying information related to the specified region. It is a diagnostic support method characterized by including. The second invention provides a diagnostic support method suitable for comparing different diseases.
  • a third invention for achieving the above-mentioned object comprises a computer, a specifying means for specifying a region of the brain associated with a plurality of diseases from a brain image, and a comparison display means for calculating and comparing information on the specified region.
  • the third invention provides a program suitable for comparing different diseases.
  • Block diagram showing functions of diagnosis support apparatus according to the present embodiment A flowchart showing the procedure of processing of the diagnosis support apparatus according to the present embodiment Flow chart showing procedure of calculation process of atrophy score Diagram showing an example of display of diagnosis support information etc. An enlarged view of the slice image Figure showing an example of discrimination of disease by combining atrophy ratio for each tissue Plot of atrophy ratio of AD and DLB
  • FIG. 1 is a block diagram showing the function of the diagnosis support apparatus 1.
  • the diagnosis support apparatus 1 includes a user interface unit 10, a processing unit 20, and a database unit 30.
  • the user interface unit 10 mainly has an image input function 11 for receiving an input of an MRI image, and a display function 13 for displaying the result processed by the processing unit 20.
  • the processing unit 20 is mainly specific to each disease to be compared with an image processing function 21 for processing an MRI image input from the user interface unit 10, a statistical processing function 23 for calculating various statistical indexes such as Z score, etc. It has a site specific function 25 for specifying a specific site (region of interest), a degree of atrophy calculation function 27 for calculating the degree of atrophy, and an atrophy ratio calculation function 29 for calculating the atrophy ratio.
  • the gray matter brain image template 31, the white matter brain image template 33, the healthy person image database 35, the region of interest ROI 37, and the like to be subjected to the processing of the processing unit 20 are stored.
  • the gray matter brain image template 31 and the white matter brain image template 33 described above are created for the gray matter and the white matter and stored in the database unit 30 in advance.
  • Each template may be created in layers according to the attributes of subjects such as age and gender.
  • DARTEL Diffeomorphic Anatomical Registration Through Exploitated Lie algebra
  • the processing of template creation using DARTEL is the same as that of Patent Document 1, and thus the description thereof is omitted.
  • FIG. 2 is a flowchart showing the processing of the diagnosis support apparatus 1 according to the present embodiment. This process can be executed by a program in the processing unit 20 comprising a computer.
  • step S1 the diagnosis support device 1 (image input function 11) receives an input of an MRI brain image of a subject.
  • step S2 the diagnosis support device 1 calculates a "atrophy score" representing the degree of brain atrophy based on the MRI brain image of the subject input in step S1.
  • the diagnosis support apparatus 1 performs "image reconstruction" on the input MRI brain image of the subject (step S21).
  • the image reconstruction first converts the input subject's MRI brain image into, for example, 100 to 200 T1-weighted MRI images captured in slices of a predetermined thickness so as to include the entire brain. At this time, the slice image is resampled so that the lengths of the sides of the voxels in each slice image become equal in advance.
  • the diagnosis support device 1 After the image reconstruction in step S21 is performed, the diagnosis support device 1 performs "tissue division" to create a gray matter brain image and a white matter brain image from which gray matter and white matter are extracted (step S22).
  • the above-mentioned T1-weighted MRI brain image includes three types of tissues: white matter exhibiting high signal value corresponding to nerve fiber, gray matter exhibiting intermediate signal value corresponding to nerve cell, and cerebrospinal fluid exhibiting low signal value. Since it is included, processing to extract gray matter and white matter is performed focusing on the difference between the signal values. Since this process is the same as the process described in Patent Document 2 in which the extraction accuracy is enhanced from Patent Document 1 and Patent Document 1, the description is omitted.
  • diagnosis support device 1 performs "anatomical standardization" on the gray matter brain image and the white matter brain image created in step S22 (step S23).
  • Anatomical standardization is the registration of voxels to a standard brain image.
  • anatomical standardization by DARTEL is performed.
  • the processing of DARTEL is the same as that of Patent Document 1, and thus the description thereof is omitted.
  • step S24 the diagnosis support device 1 compares it with the MRI image of a healthy person, and calculates a "atrophy score” indicating the degree of atrophy of the subject's brain.
  • a “Z score” which is a statistical index is used as the atrophy score.
  • a statistical comparison is made between gray matter and white matter MRI brain image groups of a healthy subject, and gray matter and white matter Z scores are calculated as follows for all voxels of the MRI brain image or voxels of a specific region.
  • the gray matter Z score is represented as Z [gray matter quality]
  • the white matter Z score is represented as Z [white matter].
  • the Z-score is a value obtained by scaling the difference between the voxel value of the subject image and the average of the corresponding voxel value of the normal subject image group by the standard deviation, and the gray matter and white matter volume It indicates the degree of relative decline.
  • the atrophy score indicating the degree of atrophy (for example, t score etc.).
  • the MRI brain images of the gray matter and white matter of the healthy person stored in the healthy person image database 35 used in step S24 are the same as those in step S21 to step S23 for the image group of the healthy person collected in advance. It is created by sequentially applying the same processing such as “structure” ⁇ “tissue division” ⁇ “anatomical standardization” and image smoothing. This process can be executed by a program in the processing unit 20 comprising a computer.
  • the atrophy score (the Z score in the present embodiment) is calculated from the MRI brain image of the subject.
  • the diagnosis support device 1 specifies brain regions (regions of interest) specific to each disease to be compared. This is mainly realized by the part specifying function 25 of the processing unit 20.
  • the diagnosis support device 1 identifies a region of interest related to each disease based on statistical processing. Specifically, when a region of interest corresponding to a certain disease is specified, an MRI image group (disease image group) of a patient having the disease and an image group (non-diseased person image group) of other people A two-sample t-test that statistically tests significant differences between the two groups in voxel units is performed, and voxels with significant differences are regarded as characteristic voxels in the disease, and a set of coordinates is associated with the disease Region of Interest (ROI). Also, as described in Japanese Patent No. 5098393, the ROI may be specified in consideration of both the significance level and the rule of thumb.
  • ROI may be specified in consideration of both the significance level and the rule of thumb.
  • the ROI may be specified only from the disease image (s). For example, with respect to a disease image (s), a region where atrophy is large may be identified as an ROI in correlation with the size of atrophy in the entire brain.
  • the ROI may be specified manually according to the subjectivity of a diagnostician or the like.
  • the region of interest ROI A disease A the region of interest ROI B disease B, will be described as those identified at step S3.
  • step S4 the diagnosis support device 1 compares and displays the diagnosis support information and the like of each portion specified in step S3.
  • the “degree of atrophy” and the “atrophy ratio” displayed in step S4 will be described. These indices are mainly calculated by the atrophy degree calculating function 25 and the atrophy ratio calculating function 27 of the processing unit 20.
  • the diagnosis support device 1 calculates a “degree of atrophy” indicating the degree of atrophy in “in the region of interest”. In addition, by calculating the degree of atrophy for each tissue of gray matter and white matter, it is possible to quantitatively evaluate the degree of atrophy of a site associated with each disease for each tissue.
  • the degree of atrophy of "white matter” in the region of interest ROI A (Equation 3) and the degree of atrophy of "white matter” (Equation 4) are calculated from the Z score as follows.
  • Atrophy of the "gray matter” in the region of interest ROI B (Equation 5), and atrophy of the "white matter” (Equation 6) is calculated as follows.
  • the “mean value of positive Z scores” in the region of interest is adopted as the degree of atrophy, but the present invention is not limited thereto, and “mean value of Z scores exceeding the threshold value is arbitrarily determined. Or simply “average value of Z score” may be adopted. Alternatively, the ratio of voxels whose Z score exceeds a threshold to the total number of voxels in the ROI may be employed.
  • the diagnosis support device 1 further calculates the “atrophy ratio” based on the atrophy degree described above.
  • the degree of atrophy described above can individually grasp the degree of atrophy in the region of interest for each disease, it is not an index that can uniquely identify the relevance of each disease, and therefore is not sufficient as an index to differentially support each disease.
  • "atrophy ratio" which is ratio of the atrophy degree of each disease calculated above is further defined, and this is used as an index of differentiation support of each disease. For example, when the disease A and the disease B are assumed, the atrophy ratio of the disease B based on the disease A is calculated as follows.
  • the atrophy ratio is also calculated for gray matter and white matter, similarly to the atrophy degree.
  • degree of atrophy of the standard disease A the denominator of the formula
  • select a tissue either “gray matter” or “white matter” in which the tendency of atrophy in the ROI A appears to be strong in patients with disease A Is desirable.
  • the tendency of the disease A is strong
  • the tendency of the disease B is strong, which can be an index for supporting identification of each disease.
  • an appropriate threshold can be set, and each disease can be discriminated in the condition that the atrophy ratio in Equations (7) and (8) is smaller than the threshold, the disease A, and the atrophy ratio is larger than the threshold, the disease B, etc. is there.
  • the degree of atrophy and ratio of atrophy of gray matter to white matter are separately calculated, but it is also possible to calculate the degree of atrophy and atrophy ratio by combining gray matter and white matter.
  • This allows the atrophy of both tissues to be assessed using one indicator.
  • This can be an effective indicator, for example, when both gray matter and white matter tissue atrophy in a certain disease, or when it can not be determined which of gray matter matter and white matter tissue atrophy.
  • a healthy subject image group prepared by combining gray matter brain images and white matter brain images is prepared in advance in the healthy subject database 35, and these image groups and gray matter brain images and white matter brain images of the subject are synthesized.
  • the Z score is calculated by comparison with the subject image, and the degree of atrophy and atrophy ratio are calculated from the Z score.
  • the Z score is calculated as follows.
  • the degree of atrophy in the region of interest ROI A of the disease A and the region of interest ROI B of the disease B is calculated as follows.
  • the atrophy ratio of the disease B based on the disease A is calculated as follows.
  • the degree of atrophy (the denominator of the formula) of the standard disease A the form of tissue in which the tendency of atrophy appears strongly in ROI A in patients with disease A ("gray matter and white matter", “gray matter”, or It is desirable to select “white matter”).
  • FIG. 4 shows a display example of the user interface unit 10 of the diagnosis support apparatus 1.
  • slice images of the brain are displayed side by side at predetermined intervals. Then, the distribution (Z score map) of the Z score (Equation 1) of "gray matter” is displayed superimposed on the slice image, and the region of interest of the disease A and the region of interest of the disease B are displayed on the slice image. Ru.
  • FIG. 5 is an enlarged view of one slice image.
  • the Z score map 5a is displayed on the slice image, and the region of interest 5b of the disease A in the slice image plane is indicated by a solid line, and the region of interest 5c of the disease B is indicated by a broken line.
  • the degree of atrophy in the entire slice image can be grasped, and the degree of atrophy of the target site (regions of interest 5b and 5c) in the slice image can be grasped.
  • slice images of the brain are displayed side by side at predetermined intervals in the display area 42 of FIG.
  • the distribution of the “white matter” Z score (Formula 2) is superimposed and displayed on the slice image.
  • the Z score there are various means for displaying the Z score, and for example, it may be displayed by changing the shading according to the value of the Z score, or may be displayed using contour lines. Further, there are various means of displaying the region of interest in each disease, and for example, the region of interest may be displayed in different colors for each disease.
  • the atrophy degree of the “white matter” of the region of interest of the disease A (shown as the site A in FIG. 4) (Equation 3) and the atrophy degree of the “white matter” (Equation 4) are displayed numerically
  • the degree of atrophy (“Eq. 5") of "the gray matter” in the region of interest of the disease B (indicated as "site B” in FIG. 4)
  • the atrophy ("Eq. 6") of the "white matter” are displayed numerically.
  • the region of interest of each disease is specified by the diagnosis support device 1, and each disease is compared and displayed using various indexes related to the region of interest of each specified disease. This provides the diagnostician with effective diagnosis support information for supporting comparison or differentiation of different diseases.
  • AD Alzheimer's disease
  • DLB Lewy body type dementia
  • AD in AD, strong atrophy is observed in the gray matter of the medial temporal region, so it is possible to support the diagnosis of AD by quantitatively evaluating atrophy of the medial temporal region using an MRI image.
  • DLB Alzheimer's disease
  • back Whitwell, Jennifer L. et al. ”Focal atrophy in dementia with Lewy bodies on MRI: a distinct pattern from Alzeimer's disease. ”Brain (2007)
  • DLB has been reported to be atrophy of the white matter of the midbrain (dorsal side), the bridge (dorsal side) and the cerebellum (Bleach (2007)) Nakatsuka, et al.
  • the site specific function 25 of the diagnosis support device 1 in the case of AD, the vicinity of the “inner temporal region” appears as a specific site In the case of DLB, the vicinity of the "rear brain stem” appeared as a specific site. Therefore, in the present embodiment, these sites are set as the regions of interest of AD and DLB.
  • the region of interest of AD near the medial temporal region
  • the region of interest of DLB near the posterior brain stem
  • the degree of atrophy calculated by the atrophy degree calculating function 27 of the diagnosis support device 1 will be examined.
  • AD as described above, since the atrophy of gray matter near the medial temporal region is large, the atrophy degree of “grey matter” based on Formula 3 was adopted.
  • DLB In DLB, according to the above-mentioned prior research, it was decided to evaluate for each tissue because there is a possibility that the gray matter and / or the white matter near the posterior brainstem may be affected. Therefore, as the degree of atrophy of DLB, it was decided to use both the degree of atrophy of "gray matter” based on Formula 5 and the degree of atrophy of "white matter” based on Formula 6.
  • the atrophy ratio calculated by the atrophy ratio calculation function 29 of the diagnosis support device 1 the atrophy ratio of gray matter based on Formula 7 (hereinafter referred to as “ ⁇ 1”), and the atrophy ratio of white matter based on Formula 8 (hereinafter, Adopted as “ ⁇ 2”.
  • the degree of atrophy of AD in ROI A near the medial temporal region
  • the atrophy degree of “grey matter” that tends to atrophy in AD patients. It was.
  • FIG. 6 shows an example in which AD and DLB are distinguished by the above-described gray matter atrophy ratio ⁇ 1 and white matter atrophy ratio ⁇ 2.
  • a threshold ⁇ 1 is set for the atrophy ratio ⁇ 1
  • a threshold ⁇ 2 is set for the atrophy ratio ⁇ 2
  • both ⁇ 1> ⁇ 1 and ⁇ 2> ⁇ 2 are satisfied, it can be determined that there is a DLB suspicion. Otherwise, it can be determined that there is suspicion of AD.
  • FIG. 7 shows a diagram in which the atrophy ratio ⁇ 1 and the atrophy ratio ⁇ 2 described above are actually calculated by the diagnosis support device 1 for AD patients and DLB patients, and the calculated values are plotted.
  • White dots indicate patients diagnosed with AD
  • black dots indicate patients diagnosed with DLB.
  • the threshold values ⁇ 1 and ⁇ 2 are both set to 0.2.
  • many DLB patients were distributed in the area satisfying .tau.1> .alpha.1 and .tau.2> .alpha.2, and many AD patients were distributed in the other area, and good discrimination results were obtained.
  • the "atrophy ratio" was effective as an index of discrimination support for AD and DLB.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Pathology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Molecular Biology (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Biophysics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Optics & Photonics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Neurology (AREA)
  • Dentistry (AREA)
  • Neurosurgery (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)

Abstract

According to the present invention, a diagnosis support device suitable for the comparison between different diseases and others are provided. In a diagnosis support device 1 according to the present invention, the input of an MRI brain image of a subject is received (step S1), and a shrinkage score, which represents the degree of shrinkage of the brain, is then calculated on the basis of the MRI brain image (step S2). Subsequently, sites to be compared in the brain are identified (step S3). Subsequently, a degree of shrinkage, which represents the degree of shrinkage of each of the identified sites, and a shrinkage ratio, which is a ratio between the degrees of shrinkage of the sites, are calculated and are then compared and displayed (step S4).

Description

医用画像表示処理方法、医用画像表示処理装置およびプログラムMEDICAL IMAGE DISPLAY PROCESSING METHOD, MEDICAL IMAGE DISPLAY PROCESSING DEVICE, AND PROGRAM
　本発明は、ＭＲＩ等により撮像された脳画像に基づき脳疾患の診断支援を行う診断支援技術に関し、特に、複数の疾患が想定される場合に適した診断支援を行う技術に関する。 The present invention relates to a diagnosis support technology that supports diagnosis of a brain disease based on a brain image captured by MRI or the like, and more particularly to a technology that performs diagnosis support that is suitable when a plurality of diseases are assumed.
　近年、ＳＰＥＣＴ（Ｓｉｎｇｌｅ　Ｐｈｏｔｏｎ　Ｅｍｉｓｓｉｏｎ　Ｃｏｍｐｕｔｅｄ　Ｔｏｍｏｇｒａｐｈｙ）やＰＥＴ（Ｐｏｓｉｔｒｏｎ　Ｅｍｉｓｓｉｏｎ　Ｔｏｍｏｇｒａｐｈｙ）等の核医学検査や、ＣＴ（Ｃｏｍｐｕｔｅｒｉｚｅｄ　Ｔｏｍｏｇｒａｐｈｙ）やＭＲＩ（Ｍａｇｎｅｔｉｃ　Ｒｅｓｏｎａｃｅ　Ｉｍａｇｉｎｇ）によって脳の状態に関する情報が取得可能になってきている。 In recent years, it has become possible to obtain information on the state of the brain by nuclear medicine examination such as SPECT (Single Photon Emission Computed Tomography) and PET (Positron Emission Tomography), CT (Computerized Tomography) and MRI (Magnetic Resonance Imaging). .
　特に、脳の組織の萎縮に関しては、ＭＲＩ画像によって特定部位の容積を求め、その相対的な大きさを比較して異常の有無を判別できる。例えば、特許文献１では、アルツハイマー型認知症の診断支援を行うシステムが開示されており、ＭＲＩ画像を用いて内側側頭部の萎縮を定量的に評価することで、アルツハイマー型認知症の診断支援を行うことを可能としている。 In particular, with regard to atrophy of brain tissue, it is possible to determine the volume of a specific site by an MRI image and compare the relative size to determine the presence or absence of abnormality. For example, Patent Document 1 discloses a system for assisting diagnosis of Alzheimer's disease, and diagnostically assessing Alzheimer's disease by quantitatively evaluating atrophy of the medial temporal region using an MRI image. It is possible to do
特許４０２５８２３号Patent 4025823 特開２０１３－６６６３２号公報JP, 2013-66632, A
　しかしながら、従来の診断支援システム等においては、特定の疾患を対象とした有効な診断支援情報は得られるものの、同時に異なる疾患が想定される場合に、これら疾患を比較する有効な診断支援情報を提供するまでには至っていない。 However, in the conventional diagnosis support system etc., although effective diagnosis support information for a specific disease can be obtained, when different diseases are assumed at the same time, effective diagnosis support information is provided to compare these diseases. It has not been done before.
　本発明は、上述した課題に鑑みてなされたものであり、その目的は、異なる疾患の比較に適した診断支援装置等を提供することである。 The present invention has been made in view of the above-described problems, and an object thereof is to provide a diagnosis support device and the like suitable for comparison of different diseases.
　前述した目的を達成するための第１の発明は、脳画像から複数の疾患に関連する脳の部位を特定する特定手段と、特定した部位に関する情報を算出し比較表示する比較表示手段と、を備えることを特徴とする診断支援装置である。第１の発明によって、異なる疾患の比較に適した診断支援装置が提供される。 According to a first aspect of the present invention for achieving the above-mentioned object, a specifying means for specifying a region of the brain associated with a plurality of diseases from a brain image, and a comparison display means for calculating and comparing and displaying information concerning the specified region. It is a diagnosis support device characterized by having. According to the first invention, a diagnostic support device suitable for comparing different diseases is provided.
　前記脳画像から脳の萎縮の程度を表す萎縮スコアを算出する算出手段を更に備え、前記比較表示手段は、前記部位とともに前記萎縮スコアの分布を脳画像に表示することが望ましい。これによって、各疾患に関連する部位とともに萎縮スコアの分布が脳画像上に表示されるため、脳画像全体の萎縮と着目部位の萎縮を視覚的に把握することができる。 It is preferable to further include calculation means for calculating an atrophy score representing the degree of atrophy of the brain from the brain image, and the comparison display means preferably displays the distribution of the atrophy score together with the site on the brain image. Since the distribution of the atrophy score is displayed on the brain image together with the region related to each disease by this, it is possible to visually grasp the atrophy of the whole brain image and the atrophy of the region of interest.
　前記比較表示手段は、前記部位における萎縮の程度を表す萎縮度を前記萎縮スコアから算出し表示することが望ましい。これによって、各疾患に関連する部位の萎縮を定量的に比較することができる。 It is desirable that the comparison display means calculate and display the atrophy degree indicating the degree of atrophy at the site from the atrophy score. By this, it is possible to quantitatively compare atrophy of the site associated with each disease.
　前記比較表示手段は、組織毎に萎縮度を表示することが望ましい。これによって、組織毎に各疾患に関連する部位の萎縮を定量的に比較することができる。 The comparison display means preferably displays the degree of atrophy for each tissue. This makes it possible to quantitatively compare atrophy of the site associated with each disease for each tissue.
　前記比較表示手段は、各部位の萎縮度の比である萎縮比を算出し表示することが望ましい。これによって、異なる疾患間の関連性を一意に把握できる鑑別支援に有効な指標が得られる。 The comparison display means preferably calculates and displays atrophy ratio which is a ratio of the atrophy degree of each part. This provides an effective indicator for discrimination support that can uniquely identify the relationship between different diseases.
　前記算出手段は、前記脳画像と健常者脳画像とを比較して前記萎縮スコアを算出することが望ましい。これによって、萎縮スコアが健常者画像との比較により算出される。 It is desirable that the calculation means calculate the atrophy score by comparing the brain image with a normal person's brain image. Thereby, the atrophy score is calculated by comparison with the healthy person image.
　前記部位は、アルツハイマー型認知症とレビー小体型認知症とで萎縮の違いが現れる脳の部位であることが望ましい。これによって、アルツハイマー型認知症とレビー小体型認知症の比較に適した診断支援が実現される。 The site is preferably a site of the brain where the difference in atrophy appears between Alzheimer's dementia and Lewy body dementia. This realizes diagnostic support suitable for comparing Alzheimer's dementia and Lewy body dementia.
　前記部位は、内側側頭部付近及び後部脳幹付近であることが望ましい。これによって、アルツハイマー型認知症とレビー小体型認知症の比較に適した診断支援が実現される。 The site is preferably near the medial temporal region and near the posterior brainstem. This realizes diagnostic support suitable for comparing Alzheimer's dementia and Lewy body dementia.
　前述した目的を達成するための第２の発明は、脳画像から複数の疾患に関連する脳の部位を特定する特定ステップと、特定した部位に関する情報を算出して比較表示する比較表示ステップ、とを含むことを特徴とする診断支援方法である。第２の発明によって、異なる疾患の比較に適した診断支援方法が提供される。 The second invention for achieving the above-mentioned object comprises a specifying step of specifying a region of the brain associated with a plurality of diseases from a brain image, and a comparison display step of calculating and comparing and displaying information related to the specified region. It is a diagnostic support method characterized by including. The second invention provides a diagnostic support method suitable for comparing different diseases.
　前述した目的を達成するための第３の発明は、コンピュータを、脳画像から複数の疾患に関連する脳の部位を特定する特定手段、特定した部位に関する情報を算出して比較表示する比較表示手段、として機能させることを特徴とするプログラムである。第３の発明によって、異なる疾患の比較に適したプログラムが提供される。 A third invention for achieving the above-mentioned object comprises a computer, a specifying means for specifying a region of the brain associated with a plurality of diseases from a brain image, and a comparison display means for calculating and comparing information on the specified region. , Is a program characterized by functioning as. The third invention provides a program suitable for comparing different diseases.
　本発明により、異なる疾患の比較に適した診断支援装置等を提供することができる。 According to the present invention, it is possible to provide a diagnostic support device and the like suitable for comparison of different diseases.
本実施形態に係る診断支援装置の機能を示すブロック図Block diagram showing functions of diagnosis support apparatus according to the present embodiment 本実施形態に係る診断支援装置の処理の手順を示すフローチャートA flowchart showing the procedure of processing of the diagnosis support apparatus according to the present embodiment 萎縮スコアの算出処理の手順を示すフローチャートFlow chart showing procedure of calculation process of atrophy score 診断支援情報等の表示の一例を示す図Diagram showing an example of display of diagnosis support information etc. スライス画像を拡大した図An enlarged view of the slice image 組織毎の萎縮比を組み合わせて疾患の判別を行う例を示す図Figure showing an example of discrimination of disease by combining atrophy ratio for each tissue ＡＤとＤＬＢの萎縮比のプロット図Plot of atrophy ratio of AD and DLB
　以下図面に基づいて、本発明の実施形態を詳細に説明する。 Hereinafter, embodiments of the present invention will be described in detail based on the drawings.
　図１は、診断支援装置１の機能を示すブロック図である。診断支援装置１は、ユーザインターフェース部１０、処理部２０、データベース部３０を有している。 FIG. 1 is a block diagram showing the function of the diagnosis support apparatus 1. The diagnosis support apparatus 1 includes a user interface unit 10, a processing unit 20, and a database unit 30.
　ユーザインターフェース部１０は、主に、ＭＲＩ画像の入力を受付ける画像入力機能１１と、処理部２０で処理された結果を表示する表示機能１３とを有する。 The user interface unit 10 mainly has an image input function 11 for receiving an input of an MRI image, and a display function 13 for displaying the result processed by the processing unit 20.
　処理部２０は、主に、ユーザインターフェース部１０から入力されたＭＲＩ画像を処理する画像処理機能２１と、Ｚスコア等の各種統計指標を算出する統計処理機能２３と、比較する各疾患に特異的な部位（関心領域）を特定する部位特定機能２５、萎縮度を算出する萎縮度算出機能２７、萎縮比を算出する萎縮比算出機能２９等を有する。 The processing unit 20 is mainly specific to each disease to be compared with an image processing function 21 for processing an MRI image input from the user interface unit 10, a statistical processing function 23 for calculating various statistical indexes such as Z score, etc. It has a site specific function 25 for specifying a specific site (region of interest), a degree of atrophy calculation function 27 for calculating the degree of atrophy, and an atrophy ratio calculation function 29 for calculating the atrophy ratio.
　また、データベース部３０には、処理部２０の処理に供する灰白質脳画像テンプレート３１、白質脳画像テンプレート３３、健常者画像データベース３５、関心領域ＲＯＩ３７等が保存されている。 Further, in the database unit 30, the gray matter brain image template 31, the white matter brain image template 33, the healthy person image database 35, the region of interest ROI 37, and the like to be subjected to the processing of the processing unit 20 are stored.
　上記の灰白質脳画像テンプレート３１、白質脳画像テンプレート３３は、灰白質と白質それぞれについて作成されたものが予め前記データベース部３０に保存されているものとする。各テンプレートは年齢や性別などの被験者の属性に応じて層別に作成されていてもよい。
　尚、本実施形態においては、上記テンプレートを作成する際の解剖学的標準化の手法としてＤＡＲＴＥＬ（Ｄｉｆｆｅｏｍｏｒｐｈｉｃ　Ａｎａｔｏｍｉｃａｌ　Ｒｅｇｉｓｔｒａｔｉｏｎ　Ｔｈｒｏｕｇｈ　Ｅｘｐｏｎｅｎｔｉａｔｅｄ　Ｌｉｅ　ａｌｇｅｂｒａ）を採用する。ＤＡＲＴＥＬを用いたテンプレート作成の処理は、特許文献１と同様であるため、記載を省略する。 It is assumed that the gray matter brain image template 31 and the white matter brain image template 33 described above are created for the gray matter and the white matter and stored in the database unit 30 in advance. Each template may be created in layers according to the attributes of subjects such as age and gender.
In the present embodiment, DARTEL (Diffeomorphic Anatomical Registration Through Exploitated Lie algebra) is adopted as a method of anatomical standardization at the time of producing the above-mentioned template. The processing of template creation using DARTEL is the same as that of Patent Document 1, and thus the description thereof is omitted.
［診断支援装置１の処理］
　図２は、本実施形態に係る診断支援装置１の処理を示すフローチャートである。尚、この処理はコンピュータからなる処理部２０においてプログラムにより実行可能なものである。 [Process of Diagnosis Support Device 1]
FIG. 2 is a flowchart showing the processing of the diagnosis support apparatus 1 according to the present embodiment. This process can be executed by a program in the processing unit 20 comprising a computer.
　ステップＳ１において、診断支援装置１（画像入力機能１１）は、被験者のＭＲＩ脳画像の入力を受付ける。 In step S1, the diagnosis support device 1 (image input function 11) receives an input of an MRI brain image of a subject.
　ステップＳ２において、診断支援装置１は、ステップＳ１において入力された被験者のＭＲＩ脳画像に基づき脳の萎縮の程度を表す「萎縮スコア」を算出する。 In step S2, the diagnosis support device 1 calculates a "atrophy score" representing the degree of brain atrophy based on the MRI brain image of the subject input in step S1.
＜萎縮スコア算出処理＞
　ここで、図３のフローチャートを参照しながら、上記ステップＳ２における萎縮スコアの算出処理を説明する。 <Atrophy score calculation processing>
Here, the process of calculating the atrophy score in step S2 will be described with reference to the flowchart of FIG. 3.
（画像再構成）
　診断支援装置１は、入力された被験者のＭＲＩ脳画像に対し「画像再構成」を行う（ステップＳ２１）。 (Image reconstruction)
The diagnosis support apparatus 1 performs "image reconstruction" on the input MRI brain image of the subject (step S21).
　画像再構成は、最初に、入力された被験者のＭＲＩ脳画像を、脳全体を含むように所定の厚さのスライス状に撮像した、例えば１００～２００枚のＴ１強調ＭＲＩ画像に変換する。この際、各スライス画像におけるボクセルの各辺の長さが予め等しくなるようにスライス画像のリサンプリングを行う。 The image reconstruction first converts the input subject's MRI brain image into, for example, 100 to 200 T1-weighted MRI images captured in slices of a predetermined thickness so as to include the entire brain. At this time, the slice image is resampled so that the lengths of the sides of the voxels in each slice image become equal in advance.
　そして、上記処理を施した被験者のＭＲＩ脳画像に対し、標準的な脳画像と空間的な位置合わせを行う。具体的には、被験者のＭＲＩ脳画像に対して、線形変換（アフィン変換）、トリミング等を施し、標準的な脳画像と位置、角度、サイズ等を合わせる。これにより、ＭＲＩ撮影時の被験者の頭の位置のずれ等が画像上で補正され、標準的な脳画像と比較する際の精度が向上する。 Then, spatial alignment with a standard brain image is performed on the MRI brain image of the subject subjected to the above processing. Specifically, linear transformation (affine transformation), trimming, and the like are performed on the subject's MRI brain image, and the position, angle, size, etc. are matched with the standard brain image. Thereby, the displacement of the position of the head of the subject at the time of MRI imaging is corrected on the image, and the accuracy in comparison with a standard brain image is improved.
（組織分割）
　ステップＳ２１の画像再構成がなされた後、診断支援装置１は「組織分割」を行い、灰白質と白質を抽出した灰白質脳画像と白質脳画像を作成する（ステップＳ２２）。 (Organization division)
After the image reconstruction in step S21 is performed, the diagnosis support device 1 performs "tissue division" to create a gray matter brain image and a white matter brain image from which gray matter and white matter are extracted (step S22).
　前述のＴ１強調ＭＲＩ脳画像には、神経線維に対応する高い信号値を呈する白質、神経細胞に対応する中間の信号値を呈する灰白質、低い信号値を呈する脳脊髄液の３種類の組織が含まれているため、この信号値の差に着目して灰白質と白質とをそれぞれ抽出する処理を行う。この処理は、特許文献１や特許文献１より抽出精度を高めた特許文献２に記載されている処理と同様であるため、記載を省略する。 The above-mentioned T1-weighted MRI brain image includes three types of tissues: white matter exhibiting high signal value corresponding to nerve fiber, gray matter exhibiting intermediate signal value corresponding to nerve cell, and cerebrospinal fluid exhibiting low signal value. Since it is included, processing to extract gray matter and white matter is performed focusing on the difference between the signal values. Since this process is the same as the process described in Patent Document 2 in which the extraction accuracy is enhanced from Patent Document 1 and Patent Document 1, the description is omitted.
（解剖学的標準化）
　そして、診断支援装置１は、ステップＳ２２において作成された灰白質脳画像及び白質脳画像に対し「解剖学的標準化」を行う（ステップＳ２３）。 (Anatomical standardization)
Then, the diagnosis support device 1 performs "anatomical standardization" on the gray matter brain image and the white matter brain image created in step S22 (step S23).
　解剖学的標準化とは、標準脳画像へのボクセルの位置合わせを行うものである。本実施形態では、ＤＡＲＴＥＬによる解剖学的標準化を実行する。ＤＡＲＴＥＬの処理については特許文献１と同様であるため、記載を省略する。 Anatomical standardization is the registration of voxels to a standard brain image. In the present embodiment, anatomical standardization by DARTEL is performed. The processing of DARTEL is the same as that of Patent Document 1, and thus the description thereof is omitted.
　ＤＡＲＴＥＬによる解剖学的標準化を施した灰白質脳画像と白質脳画像に対して、Ｓ／Ｎ比の向上等を目的に、画像平滑化の処理を行う。このように画像平滑化を行うことにより、解剖学的標準化処理で完全に一致しない個体差を低減させることができる。こちらも具体的な処理については、特許文献１と同様である。 Performs image smoothing processing on gray matter brain images and white matter brain images that have been anatomically standardized by DARTEL for the purpose of improving the S / N ratio, etc. By performing image smoothing in this manner, individual differences that do not completely match in the anatomical standardization process can be reduced. The specific process is also similar to that of Patent Document 1.
　また、その後、比較対象となる健常者の画像群におけるボクセル値の分布と合わせるために、脳全体のボクセル値を補正する濃度値補正を行う。 After that, in order to match the distribution of voxel values in the image group of a healthy subject to be compared, density value correction is performed to correct voxel values of the whole brain.
（比較）
　ステップＳ２４において、診断支援装置１は、健常者のＭＲＩ画像との比較を行い、被験者の脳の萎縮の程度を示す「萎縮スコア」を算出する。本実施形態では、萎縮スコアとして統計的指標である「Ｚスコア」を用いる。 (Comparison)
In step S24, the diagnosis support device 1 compares it with the MRI image of a healthy person, and calculates a "atrophy score" indicating the degree of atrophy of the subject's brain. In the present embodiment, a “Z score” which is a statistical index is used as the atrophy score.
　具体的には、上記したステップＳ２３により解剖学的標準化、画像平滑化等を施した被験者の灰白質脳画像及び白質脳画像と、予め収集して前記データベース部３０の健常者画像データベース３５に保存してある健常者の灰白質及び白質のＭＲＩ脳画像群との統計的比較を行い、ＭＲＩ脳画像の全ボクセル又は特定領域のボクセルについて灰白質及び白質のＺスコアを次のように算出する。以降、灰白質のＺスコアをＺ[灰白質]、白質のＺスコアをＺ[白質]と表す。 Specifically, gray matter brain images and white matter brain images of subjects subjected to anatomical standardization, image smoothing, etc. in step S23 described above, and collected in advance and stored in the healthy person image database 35 of the database unit 30. A statistical comparison is made between gray matter and white matter MRI brain image groups of a healthy subject, and gray matter and white matter Z scores are calculated as follows for all voxels of the MRI brain image or voxels of a specific region. Hereinafter, the gray matter Z score is represented as Z [gray matter quality], and the white matter Z score is represented as Z [white matter].
Figure JPOXMLDOC01-appb-M000001
Figure JPOXMLDOC01-appb-M000001
Figure JPOXMLDOC01-appb-M000002
Figure JPOXMLDOC01-appb-M000002
　上式に示すように、Ｚスコアは、被験者画像のボクセル値と、健常者画像群の対応するボクセル値の平均との差を、標準偏差によってスケーリングした値であり、灰白質及び白質の容積の相対的低下の度合を示すものである。 As shown in the above equation, the Z-score is a value obtained by scaling the difference between the voxel value of the subject image and the average of the corresponding voxel value of the normal subject image group by the standard deviation, and the gray matter and white matter volume It indicates the degree of relative decline.
　尚、Ｚスコアに限らず、被験者画像と健常者画像とのボクセル値の大小が判断できるその他の指標を萎縮の程度を示す萎縮スコアとして用いてもよい（例えばｔスコア等）。 In addition to the Z score, another index by which the magnitude of the voxel value between the subject image and the healthy person image can be determined may be used as the atrophy score indicating the degree of atrophy (for example, t score etc.).
　また、ステップＳ２４において使用した健常者画像データベース３５に保存される健常者の灰白質及び白質のＭＲＩ脳画像は、予め収集した健常者の画像群のそれぞれに対しステップＳ２１～ステップＳ２３の「画像再構成」→「組織分割」→「解剖学的標準化」及び画像平滑化等の同様の処理を順次適用して作成されたものである。尚、この処理はコンピュータからなる処理部２０においてプログラムにより実行可能なものである。 In addition, the MRI brain images of the gray matter and white matter of the healthy person stored in the healthy person image database 35 used in step S24 are the same as those in step S21 to step S23 for the image group of the healthy person collected in advance. It is created by sequentially applying the same processing such as “structure” → “tissue division” → “anatomical standardization” and image smoothing. This process can be executed by a program in the processing unit 20 comprising a computer.
　以上説明した処理により、被験者のＭＲＩ脳画像から萎縮スコア（本実施形態ではＺスコア）が算出される。 By the processing described above, the atrophy score (the Z score in the present embodiment) is calculated from the MRI brain image of the subject.
　図２のフローチャートに戻る。ステップＳ３において、診断支援装置１は、比較する各疾患に特異的な脳の部位（関心領域）を特定する。これは主に、処理部２０の部位特定機能２５により実現される。 It returns to the flowchart of FIG. In step S3, the diagnosis support device 1 specifies brain regions (regions of interest) specific to each disease to be compared. This is mainly realized by the part specifying function 25 of the processing unit 20.
　例えば、診断支援装置１は、統計的処理に基づいて各疾患に関連する関心領域を特定する。具体的には、ある疾患に対応する関心領域を特定する場合、その疾患を持つ患者のＭＲＩ画像群（疾患画像群）と、それ以外の人の画像群（非疾患者画像群）とについて、ボクセル単位で２群間の有意差を統計的に検定する２標本t検定を行い、有意差が認められたボクセルを、その疾患における特徴的なボクセルとみなし、その座標の集合をその疾患に対応する関心領域（Ｒｅｇｉｏｎ　Ｏｆ　Ｉｎｔｅｒｅｓｔ：ＲＯＩ）として特定する。
　また、特許５０９８３９３号記載のように有意水準と経験則の両方を考慮してＲＯＩを特定してもよい。
　また、疾患画像（群）のみからＲＯＩを特定してもよい。例えば、疾患画像（群）について、脳全体における萎縮の大きさに相関して萎縮が大きい部位をＲＯＩとして特定してもよい。
　その他、診断者等の主観により手動でＲＯＩを特定してもよい。 For example, the diagnosis support device 1 identifies a region of interest related to each disease based on statistical processing. Specifically, when a region of interest corresponding to a certain disease is specified, an MRI image group (disease image group) of a patient having the disease and an image group (non-diseased person image group) of other people A two-sample t-test that statistically tests significant differences between the two groups in voxel units is performed, and voxels with significant differences are regarded as characteristic voxels in the disease, and a set of coordinates is associated with the disease Region of Interest (ROI).
Also, as described in Japanese Patent No. 5098393, the ROI may be specified in consideration of both the significance level and the rule of thumb.
Alternatively, the ROI may be specified only from the disease image (s). For example, with respect to a disease image (s), a region where atrophy is large may be identified as an ROI in correlation with the size of atrophy in the entire brain.
In addition, the ROI may be specified manually according to the subjectivity of a diagnostician or the like.
　以降、本実施形態においては異なる疾患Ａと疾患Ｂを想定し、疾患Ａの関心領域ＲＯＩＡ、疾患Ｂの関心領域ＲＯＩＢが、ステップＳ３において特定されたものとして説明を行う。 Hereinafter, assuming a different disease A and disease B in this embodiment, the region of interest ROI A disease A, the region of interest ROI B disease B, will be described as those identified at step S3.
（比較表示）
　ステップＳ４において、診断支援装置１は、ステップＳ３において特定した各部位の診断支援情報等を比較表示する。 (Comparison display)
In step S4, the diagnosis support device 1 compares and displays the diagnosis support information and the like of each portion specified in step S3.
　ここで、ステップＳ４において表示される「萎縮度」及び「萎縮比」について説明する。これらの指標は、主に、処理部２０の萎縮度算出機能２５、萎縮比算出機能２７により算出される。 Here, the “degree of atrophy” and the “atrophy ratio” displayed in step S4 will be described. These indices are mainly calculated by the atrophy degree calculating function 25 and the atrophy ratio calculating function 27 of the processing unit 20.
＜萎縮度＞
　診断支援装置１は、「関心領域内」における萎縮の程度を示す「萎縮度」を算出する。また、萎縮度を灰白質及び白質の組織毎に算出することで、各疾患に関連する部位の萎縮の程度を組織毎に定量的に評価することができるようにする。 Degree of atrophy
The diagnosis support device 1 calculates a “degree of atrophy” indicating the degree of atrophy in “in the region of interest”. In addition, by calculating the degree of atrophy for each tissue of gray matter and white matter, it is possible to quantitatively evaluate the degree of atrophy of a site associated with each disease for each tissue.
　具体的には、関心領域ＲＯＩＡ内の「灰白質」の萎縮度（数式３）、及び「白質」の萎縮度（数式４）は次のようにＺスコアから算出される。 Specifically, the degree of atrophy of "white matter" in the region of interest ROI A (Equation 3) and the degree of atrophy of "white matter" (Equation 4) are calculated from the Z score as follows.
Figure JPOXMLDOC01-appb-M000003
Figure JPOXMLDOC01-appb-M000003
Figure JPOXMLDOC01-appb-M000004
Figure JPOXMLDOC01-appb-M000004
　また、関心領域ＲＯＩＢ内の「灰白質」の萎縮度（数式５）、及び「白質」の萎縮度（数式６）は次のように算出される。 Also, atrophy of the "gray matter" in the region of interest ROI B (Equation 5), and atrophy of the "white matter" (Equation 6) is calculated as follows.
Figure JPOXMLDOC01-appb-M000005
Figure JPOXMLDOC01-appb-M000005
Figure JPOXMLDOC01-appb-M000006
Figure JPOXMLDOC01-appb-M000006
　尚、本実施形態では、萎縮度として関心領域内の「正のＺスコアの平均値」を採用しているが、これに限らず、任意に閾値を定めた「閾値を超えるＺスコアの平均値」または単に「Ｚスコアの平均値」を採用してもよい。また、ＲＯＩ内の総ボクセル数に対してＺスコアが閾値を超えるボクセルが占める割合を採用してもよい。 In the present embodiment, the “mean value of positive Z scores” in the region of interest is adopted as the degree of atrophy, but the present invention is not limited thereto, and “mean value of Z scores exceeding the threshold value is arbitrarily determined. Or simply “average value of Z score” may be adopted. Alternatively, the ratio of voxels whose Z score exceeds a threshold to the total number of voxels in the ROI may be employed.
＜萎縮比＞
　診断支援装置１は、上記した萎縮度に基づき更に「萎縮比」を算出する。ここで、「萎縮比」とは異なる疾患が想定されるときにある疾患を基準として他の疾患の特徴がどれだけ大きいかを示す指標のことを言う。前述した萎縮度は、疾患毎の関心領域における萎縮の程度を個別的に把握できるものの、各疾患の関連性を一意に把握できる指標ではないため、各疾患を鑑別支援する指標としては十分ではない。そこで、本実施形態では、更に、上記算出した各疾患の萎縮度の比である「萎縮比」を定義し、これを各疾患の鑑別支援の指標として用いる。
　例えば、疾患Ａ、疾患Ｂが想定される場合、疾患Ａを基準とした疾患Ｂの萎縮比は次のように算出される。 <Atrophy ratio>
The diagnosis support device 1 further calculates the “atrophy ratio” based on the atrophy degree described above. Here, when a disease different from the “atrophy ratio” is assumed, it refers to an index indicating how large the feature of another disease is based on the certain disease. Although the degree of atrophy described above can individually grasp the degree of atrophy in the region of interest for each disease, it is not an index that can uniquely identify the relevance of each disease, and therefore is not sufficient as an index to differentially support each disease. . So, in this embodiment, "atrophy ratio" which is ratio of the atrophy degree of each disease calculated above is further defined, and this is used as an index of differentiation support of each disease.
For example, when the disease A and the disease B are assumed, the atrophy ratio of the disease B based on the disease A is calculated as follows.
Figure JPOXMLDOC01-appb-M000007
Figure JPOXMLDOC01-appb-M000007
Figure JPOXMLDOC01-appb-M000008
Figure JPOXMLDOC01-appb-M000008
　萎縮比も萎縮度と同様に、灰白質及び白質について算出する。尚、基準となる疾患Ａの萎縮度（数式の分母）については、疾患Ａの患者においてＲＯＩＡ内で萎縮の傾向が強く現れる組織（「灰白質」又は「白質」のいずれか）を選択することが望ましい。
　上式により、萎縮比の値が小さいと疾患Ａの傾向が強く、萎縮比の値が大きいと疾患Ｂの傾向が強いものと判断でき、各疾患の鑑別を支援する指標となりうる。例えば、適切な閾値を設定し、数式（７）（８）の萎縮比が閾値より小さい場合には疾患Ａ、萎縮比が閾値より大きい場合には疾患Ｂ、といった具合に各疾患を判別可能である。 The atrophy ratio is also calculated for gray matter and white matter, similarly to the atrophy degree. As for the degree of atrophy of the standard disease A (the denominator of the formula), select a tissue (either “gray matter” or “white matter”) in which the tendency of atrophy in the ROI A appears to be strong in patients with disease A Is desirable.
According to the above equation, when the value of the atrophy ratio is small, the tendency of the disease A is strong, and when the value of the atrophy ratio is large, it can be determined that the tendency of the disease B is strong, which can be an index for supporting identification of each disease. For example, an appropriate threshold can be set, and each disease can be discriminated in the condition that the atrophy ratio in Equations (7) and (8) is smaller than the threshold, the disease A, and the atrophy ratio is larger than the threshold, the disease B, etc. is there.
　尚、本実施形態においては、灰白質と白質の萎縮度及び萎縮比を個別的に算出しているが、灰白質と白質を合成して１つの萎縮度及び萎縮比を算出してもよい。これにより、両方の組織の萎縮を１つの指標を用いて評価できる。これは、例えば、ある疾患において灰白質及び白質の両方の組織が萎縮するような場合、若しくは、灰白質及び白質のいずれの組織が萎縮するかを判断できないような場合に有効な指標となりうる。
　但し、この場合、健常者データベース３５には予め灰白質脳画像と白質脳画像を合成した健常者画像群が予め用意されており、これら画像群と被験者の灰白質脳画像及び白質脳画像を合成した被験者画像との比較により、Ｚスコアを算出し、当該Ｚスコアから萎縮度及び萎縮比を算出する。 In the present embodiment, the degree of atrophy and ratio of atrophy of gray matter to white matter are separately calculated, but it is also possible to calculate the degree of atrophy and atrophy ratio by combining gray matter and white matter. This allows the atrophy of both tissues to be assessed using one indicator. This can be an effective indicator, for example, when both gray matter and white matter tissue atrophy in a certain disease, or when it can not be determined which of gray matter matter and white matter tissue atrophy.
However, in this case, a healthy subject image group prepared by combining gray matter brain images and white matter brain images is prepared in advance in the healthy subject database 35, and these image groups and gray matter brain images and white matter brain images of the subject are synthesized. The Z score is calculated by comparison with the subject image, and the degree of atrophy and atrophy ratio are calculated from the Z score.
　例えば、Ｚスコアは下記のように算出される。 For example, the Z score is calculated as follows.
Figure JPOXMLDOC01-appb-M000009
Figure JPOXMLDOC01-appb-M000009
　また、疾患Ａの関心領域ＲＯＩＡ、疾患Ｂの関心領域ＲＯＩＢにおける萎縮度は次のように算出される。 Further, the degree of atrophy in the region of interest ROI A of the disease A and the region of interest ROI B of the disease B is calculated as follows.
Figure JPOXMLDOC01-appb-M000010
Figure JPOXMLDOC01-appb-M000010
Figure JPOXMLDOC01-appb-M000011
Figure JPOXMLDOC01-appb-M000011
　さらに、上記した萎縮度から例えば疾患Ａを基準とした疾患Ｂの萎縮比は次のように算出される。 Furthermore, from the degree of atrophy described above, for example, the atrophy ratio of the disease B based on the disease A is calculated as follows.
Figure JPOXMLDOC01-appb-M000012
Figure JPOXMLDOC01-appb-M000012
　尚、基準となる疾患Ａの萎縮度（数式の分母）については、疾患Ａの患者においてＲＯＩＡ内で萎縮の傾向が強く現れる組織の形態（「灰白質及び白質」、「灰白質」、又は「白質」のいずれか）を選択することが望ましい。 With regard to the degree of atrophy (the denominator of the formula) of the standard disease A, the form of tissue in which the tendency of atrophy appears strongly in ROI A in patients with disease A ("gray matter and white matter", "gray matter", or It is desirable to select “white matter”).
　以上説明した種々の指標（Ｚスコア、萎縮度、萎縮比）は、ユーザインターフェース部１０（表示機能１３）に表示される。
　図４は、診断支援装置１のユーザインターフェース部１０の表示例を示す。 The various indexes (Z score, degree of atrophy, atrophy ratio) described above are displayed on the user interface unit 10 (display function 13).
FIG. 4 shows a display example of the user interface unit 10 of the diagnosis support apparatus 1.
　図４の表示エリア４１には、脳のスライス画像が所定間隔おきに並べて表示される。そして、スライス画像上に「灰白質」のＺスコア（数式１）の分布（Ｚスコアマップ）が重ねて表示され、また、スライス画像上に疾患Ａの関心領域と疾患Ｂの関心領域が表示される。 In the display area 41 of FIG. 4, slice images of the brain are displayed side by side at predetermined intervals. Then, the distribution (Z score map) of the Z score (Equation 1) of "gray matter" is displayed superimposed on the slice image, and the region of interest of the disease A and the region of interest of the disease B are displayed on the slice image. Ru.
　図５は、一枚のスライス画像を拡大した図である。スライス画像上に、Ｚスコアマップ５ａが表示され、また、スライス画像面での疾患Ａの関心領域５ｂが実線、疾患Ｂの関心領域５ｃが破線で表示される。これにより、スライス画像全体での萎縮の程度を把握できるとともに、スライス画像中の着目部位（関心領域５ｂ、５ｃ）の萎縮の程度を把握することができる。 FIG. 5 is an enlarged view of one slice image. The Z score map 5a is displayed on the slice image, and the region of interest 5b of the disease A in the slice image plane is indicated by a solid line, and the region of interest 5c of the disease B is indicated by a broken line. Thus, the degree of atrophy in the entire slice image can be grasped, and the degree of atrophy of the target site (regions of interest 5b and 5c) in the slice image can be grasped.
　図４の表示エリア４２には、表示エリア４１と同様に脳のスライス画像が所定間隔おきに並べて表示される。但し、表示エリア４２においては、スライス画像上に「白質」のＺスコア（数式２）の分布が重ねて表示される。 Similar to the display area 41, slice images of the brain are displayed side by side at predetermined intervals in the display area 42 of FIG. However, in the display area 42, the distribution of the “white matter” Z score (Formula 2) is superimposed and displayed on the slice image.
　このように表示エリア４１及び表示エリア４２において、組織毎（灰白質、白質）にＺスコアの分布を表示することで、組織毎の萎縮の違いを把握することができる。 As described above, by displaying the distribution of the Z score for each tissue (gray matter and white matter) in the display area 41 and the display area 42, it is possible to grasp the difference in atrophy between the tissues.
　尚、Ｚスコアの表示の手段は様々であり、例えば、Ｚスコアの値に応じて濃淡を変えて表示してもよいし、等高線を用いて表示してもよい。また、各疾患における関心領域の表示の手段も様々であり、例えば、疾患ごとに関心領域を色分けして表示するようにしてもよい。 Note that there are various means for displaying the Z score, and for example, it may be displayed by changing the shading according to the value of the Z score, or may be displayed using contour lines. Further, there are various means of displaying the region of interest in each disease, and for example, the region of interest may be displayed in different colors for each disease.
　図４の表示エリア４３には、疾患Ａの関心領域（図４では部位Ａと示す）の「灰白質」の萎縮度（数式３）、及び「白質」の萎縮度（数式４）が数値表示され、また、疾患Ｂの関心領域（図４では部位Ｂと示す）の「灰白質」の萎縮度（数式５）、及び「白質」の萎縮度（数式６）が数値表示される。 In the display area 43 of FIG. 4, the atrophy degree of the “white matter” of the region of interest of the disease A (shown as the site A in FIG. 4) (Equation 3) and the atrophy degree of the “white matter” (Equation 4) are displayed numerically In addition, the degree of atrophy ("Eq. 5") of "the gray matter" in the region of interest of the disease B (indicated as "site B" in FIG. 4) and the atrophy ("Eq. 6") of the "white matter" are displayed numerically.
　そして、図４の表示エリア４４には、疾患Ａを基準とした疾患Ｂの「灰白質」の萎縮比（数式７）、及び「白質」の萎縮比（数式８）が数値表示される。 Then, in the display area 44 of FIG. 4, the atrophy ratio of the “white matter” of the disease B with reference to the disease A (Equation 7) and the atrophy ratio of the “white matter” (Equation 8) are numerically displayed.
　以上、本実施形態においては、診断支援装置１によって、各疾患の関心領域が特定され、特定した各疾患の関心領域に関する種々の指標を用いて各疾患を比較表示する。これにより、異なる疾患を比較又は鑑別支援する有効な診断支援情報が診断者に提供される。 As described above, in the present embodiment, the region of interest of each disease is specified by the diagnosis support device 1, and each disease is compared and displayed using various indexes related to the region of interest of each specified disease. This provides the diagnostician with effective diagnosis support information for supporting comparison or differentiation of different diseases.
[実施例]
　ここでは、一実施例として、アルツハイマー型認知症（以下、「ＡＤ」と呼ぶ）とレビー小体型認知症（以下、「ＤＬＢ」と呼ぶ）の２つの疾患を対象として鑑別支援の可能性を検証した。 [Example]
Here, as an example, the possibility of differentiation support was examined for two diseases, Alzheimer's disease (hereinafter referred to as "AD") and Lewy body type dementia (hereinafter referred to as "DLB"). did.
　このうち、ＡＤにおいては、内側側頭部の灰白質に強い萎縮が観測されるため、ＭＲＩ画像を用いて内側側頭部の萎縮を定量的に評価することで、ＡＤの診断支援が可能であることは既に知られている。 Among them, in AD, strong atrophy is observed in the gray matter of the medial temporal region, so it is possible to support the diagnosis of AD by quantitatively evaluating atrophy of the medial temporal region using an MRI image. Some things are already known.
　一方、ＤＬＢに関しては、ＭＲＩにおける疾患特異性について未だエビデンスが少ないのが現状である。しかしながら、近年の研究により、ＤＬＢは中脳（背側）の灰白質が萎縮するとの報告がなされている（
Whitwell, Jennifer L．et al．”Focal atrophy in dementia with Lewy bodies on MRI: a distinct
pattern from Alzeimer’s disease.” Brain(2007) ）。また、別の研究によれば、ＤＬＢは中脳（背側）・橋（背側）・小脳の白質が萎縮するとの報告がなされている（
Nakatsuka, et al. “Discrimination of dementia with Lewy bodies
from Alzheimer’s disease using voxel-based morphometry of white matter by
statistical parametric mapping 8 plus diffeomorphic anatomic registration
through exponentiated Lie algebra.” Neuroradiology(2013) ）。これら先行研究の知見によれば、ＤＬＢにおいては後部脳幹付近に特異な傾向があるものと推測される。 On the other hand, with regard to DLB, at present there is little evidence about disease specificity in MRI. However, recent studies have reported that DLB is atrophy of gray matter in the midbrain (back) (
Whitwell, Jennifer L. et al. ”Focal atrophy in dementia with Lewy bodies on MRI: a distinct
pattern from Alzeimer's disease. ”Brain (2007)) Also, according to another study, DLB has been reported to be atrophy of the white matter of the midbrain (dorsal side), the bridge (dorsal side) and the cerebellum (Bleach (2007))
Nakatsuka, et al. “Discrimination of dementia with Lewy bodies
from Alzheimer's disease using voxel-based geometry of white matter by
statistical parametric mapping 8 plus diffeomorphic anatomical registration
Through expansiated Lie algebra. "Neuroradiology (2013)) According to the findings of these previous studies, it is speculated that in DLB, there is a unique tendency near the posterior brainstem.
　実際に、診断支援装置１の部位特定機能２５によりＡＤ及びＤＬＢに特異的な部位（萎縮が大きい部位）を特定した結果、ＡＤの場合は「内側側頭部」付近が特異的な部位として現れ、ＤＬＢの場合は「後部脳幹」付近が特異的な部位として現れた。そこで、本実施例では、これら部位をＡＤとＤＬＢの関心領域に設定した。ここで、ＡＤの関心領域（内側側頭部付近）をＲＯＩＡ、ＤＬＢの関心領域（後部脳幹付近）をＲＯＩＢとする。 In fact, as a result of specifying a site specific to AD and DLB (a site with large atrophy) by the site specific function 25 of the diagnosis support device 1, in the case of AD, the vicinity of the “inner temporal region” appears as a specific site In the case of DLB, the vicinity of the "rear brain stem" appeared as a specific site. Therefore, in the present embodiment, these sites are set as the regions of interest of AD and DLB. Here, the region of interest of AD (near the medial temporal region) is ROI A , and the region of interest of DLB (near the posterior brain stem) is ROI B.
　次に、診断支援装置１の萎縮度算出機能２７により算出する萎縮度を検討する。ＡＤにおいては、前述したように内側側頭部付近の灰白質の萎縮が大きいため、数式３に基づく「灰白質」の萎縮度を採用した。ＤＬＢにおいては、前述した先行研究によれば、後部脳幹付近の灰白質、白質のいずれか又はその両方に影響が出る可能性があるため、組織毎に評価することとした。そこで、ＤＬＢの萎縮度として、数式５に基づく「灰白質」の萎縮度、及び数式６に基づく「白質」の萎縮度の両方を利用することとした。 Next, the degree of atrophy calculated by the atrophy degree calculating function 27 of the diagnosis support device 1 will be examined. In AD, as described above, since the atrophy of gray matter near the medial temporal region is large, the atrophy degree of “grey matter” based on Formula 3 was adopted. In DLB, according to the above-mentioned prior research, it was decided to evaluate for each tissue because there is a possibility that the gray matter and / or the white matter near the posterior brainstem may be affected. Therefore, as the degree of atrophy of DLB, it was decided to use both the degree of atrophy of "gray matter" based on Formula 5 and the degree of atrophy of "white matter" based on Formula 6.
　そして、診断支援装置１の萎縮比算出機能２９により算出する萎縮比として、数式７に基づく灰白質の萎縮比（以降、「τ１」と示す）、及び数式８に基づく白質の萎縮比（以降、「τ２」と示す）を採用した。ここで、数式７、８の萎縮比の分母に相当するＲＯＩＡ（内側側頭部付近）内のＡＤの萎縮度は、ＡＤ患者に萎縮の傾向が大きく表れる「灰白質」の萎縮度を用いた。 Then, as the atrophy ratio calculated by the atrophy ratio calculation function 29 of the diagnosis support device 1, the atrophy ratio of gray matter based on Formula 7 (hereinafter referred to as “τ1”), and the atrophy ratio of white matter based on Formula 8 (hereinafter, Adopted as “τ2”. Here, the degree of atrophy of AD in ROI A (near the medial temporal region) corresponding to the denominator of the atrophy ratio of Equations 7 and 8 uses the atrophy degree of “grey matter” that tends to atrophy in AD patients. It was.
　図６は、上記した灰白質の萎縮比τ１及び白質の萎縮比τ２によりＡＤとＤＬＢを判別する一例を示す。
　図６に示すように、萎縮比τ１に対して閾値α１、萎縮比τ２に対して閾値α２を設定し、τ１＞α１及びτ２＞α２の両方を満たす場合、ＤＬＢの疑いがあると判別できる。それ以外の場合は、ＡＤの疑いがあると判別できる。 FIG. 6 shows an example in which AD and DLB are distinguished by the above-described gray matter atrophy ratio τ1 and white matter atrophy ratio τ2.
As shown in FIG. 6, when a threshold α1 is set for the atrophy ratio τ1 and a threshold α2 is set for the atrophy ratio τ2, and both τ1> α1 and τ2> α2 are satisfied, it can be determined that there is a DLB suspicion. Otherwise, it can be determined that there is suspicion of AD.
　図７は、実際にＡＤの患者とＤＬＢの患者を対象として上記した萎縮比τ１及び萎縮比τ２を診断支援装置１により算出し、算出した値をプロットした図を示す。白色のドットがＡＤと診断された患者を示し、黒色のドットがＤＬＢと診断された患者を示す。本実施形態では閾値α１、α２はともに０．２に設定した。
　図７に示すようにτ１＞α１及びτ２＞α２を満たすエリアにＤＬＢ患者が多く分布し、それ以外のエリアにＡＤ患者が多く分布しているのが分かり、良好な判別結果が得られた。これにより「萎縮比」がＡＤとＤＬＢを対象とした鑑別支援の指標として有効であることが確認された。 FIG. 7 shows a diagram in which the atrophy ratio τ1 and the atrophy ratio τ2 described above are actually calculated by the diagnosis support device 1 for AD patients and DLB patients, and the calculated values are plotted. White dots indicate patients diagnosed with AD, black dots indicate patients diagnosed with DLB. In the present embodiment, the threshold values α1 and α2 are both set to 0.2.
As shown in FIG. 7, many DLB patients were distributed in the area satisfying .tau.1> .alpha.1 and .tau.2> .alpha.2, and many AD patients were distributed in the other area, and good discrimination results were obtained. Thus, it was confirmed that the "atrophy ratio" was effective as an index of discrimination support for AD and DLB.
　以上、添付図面を参照しながら、本発明の好適な実施形態について説明したが、本発明はかかる例に限定されない。当業者であれば、本願で開示した技術的思想の範疇内において、各種の変更例又は修正例に想到し得ることは明らかであり、それらについても当然に本発明の技術的範囲に属するものと了解される。 Although the preferred embodiments of the present invention have been described above with reference to the accompanying drawings, the present invention is not limited to such examples. It is apparent that those skilled in the art can conceive of various modifications or alterations within the scope of the technical idea disclosed in the present application, and of course these also fall within the technical scope of the present invention. It is understood.
　１・・・・診断支援装置
　１０・・・ユーザインターフェース部
　１１・・・画像入力機能
　１３・・・表示機能
　２０・・・処理部
　２１・・・画像処理機能
　２３・・・統計処理機能
　２５・・・部位特定機能
　２７・・・萎縮度算出機能
　２９・・・萎縮比算出機能
　３０・・・データベース部
　３１・・・灰白質脳画像テンプレート
　３３・・・白質脳画像テンプレート
　３５・・・健常者データベース
　３７・・・関心領域ＲＯＩ 1 ... Diagnosis support device 10 ... User interface unit 11 ... Image input function 13 ... Display function 20 ... Processing unit 21 ... Image processing function 23 ... Statistical processing function 25 · · · Site identification function 27 · · · atrophy degree calculation function 29 · · · atrophy ratio calculation function 30 · · · · · · database portion 31 · gray matter brain image template 33 · · · white matter brain image template 35 · · · healthy people Database 37 ··· Region of interest ROI

Claims (10)

  1. 　脳画像から複数の疾患に関連する脳の部位を特定する特定手段と、
    　特定した部位に関する情報を算出し比較表示する比較表示手段と、
    　を備えることを特徴とする診断支援装置。     Specifying means for specifying a region of the brain associated with a plurality of diseases from brain images;
    Comparison display means for calculating and comparing and displaying information related to the identified part;
    A diagnostic support apparatus comprising:
  2. 　前記脳画像から脳の萎縮の程度を表す萎縮スコアを算出する算出手段を更に備え、
    　前記比較表示手段は、前記部位とともに前記萎縮スコアの分布を脳画像に表示することを特徴とする請求項１に記載の診断支援装置。     It further comprises a calculation means for calculating an atrophy score representing the degree of atrophy of the brain from the brain image,
    The diagnosis support device according to claim 1, wherein the comparison display means displays the distribution of the atrophy score together with the site on a brain image.
  3. 　前記比較表示手段は、前記部位における萎縮の程度を表す萎縮度を前記萎縮スコアから算出し表示することを特徴とする請求項２に記載の診断支援装置。 The diagnosis support device according to claim 2, wherein the comparison display means calculates and displays the atrophy degree indicating the degree of atrophy at the site from the atrophy score.
  4. 　前記比較表示手段は、組織毎に萎縮度を表示することを特徴とする請求項３に記載の診断支援装置。 The diagnostic support device according to claim 3, wherein the comparison display means displays the degree of atrophy for each tissue.
  5. 　前記比較表示手段は、各部位の萎縮度の比である萎縮比を算出し表示することを特徴とする請求項３又は請求項４に記載の診断支援装置。 The diagnosis support device according to claim 3 or 4, wherein the comparison display means calculates and displays atrophy ratio which is a ratio of the atrophy degree of each part.
  6. 　前記算出手段は、前記脳画像と健常者脳画像とを比較して前記萎縮スコアを算出することを特徴とする請求項２乃至請求項５のいずれか１項に記載の診断支援装置。 The diagnosis support device according to any one of claims 2 to 5, wherein the calculation means calculates the atrophy score by comparing the brain image and a brain image of a healthy person.
  7. 　前記部位は、アルツハイマー型認知症とレビー小体型認知症とで萎縮の違いが現れる脳の部位であることを特徴とする請求項１乃至請求項６のいずれか１項に記載の診断支援装置。 The said site | part is a site | part of the brain in which the difference of atrophy appears in Alzheimer type dementia and Lewy body type dementia, The diagnostic assistance apparatus of any one of the Claims 1 thru | or 6 characterized by the above-mentioned.
  8. 　前記部位は、内側側頭部付近及び後部脳幹付近であることを特徴とする請求項１乃至請求項７のいずれか１項に記載の診断支援装置。 The diagnosis support apparatus according to any one of claims 1 to 7, wherein the site is near the medial temporal region and near the posterior brainstem.
  9. 　脳画像から複数の疾患に関連する脳の部位を特定する特定ステップと、
    　特定した部位に関する情報を算出して比較表示する比較表示ステップと、
    　を含むことを特徴とする診断支援方法。     Identifying the location of the brain associated with a plurality of diseases from the brain image;
    A comparison display step of calculating and comparing and displaying information related to the identified part;
    A diagnostic support method characterized in that
  10. 　コンピュータを、
    　脳画像から複数の疾患に関連する脳の部位を特定する特定手段、
    　特定した部位に関する情報を算出して比較表示する比較表示手段、として機能させることを特徴とするプログラム。     Computer,
    Specifying means for specifying a region of the brain associated with a plurality of diseases from brain images;
    A program characterized in that it functions as comparison display means for calculating and comparing and displaying information related to a specified part.
PCT/JP2015/076918 2014-09-25 2015-09-24 Medical image display processing method, medical image display processing device, and program WO2016047683A1 (en)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CN201580047080.9A CN106659424B (en) 2014-09-25 2015-09-24 Medical image display processing method, medical image display processing device, and program
ES15845121T ES2857099T3 (en) 2014-09-25 2015-09-24 Medical image display processing method, medical image display processing device and program
US15/504,774 US10285657B2 (en) 2014-09-25 2015-09-24 Medical image display processing method, medical image display processing device, and program
EP15845121.1A EP3199102B1 (en) 2014-09-25 2015-09-24 Medical image display processing method, medical image display processing device, and program

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2014-194786 2014-09-25
JP2014194786A JP2016064004A (en) 2014-09-25 2014-09-25 Medical image display processing method, medical image display processing device and program

Publications (1)

Publication Number Publication Date
WO2016047683A1 true WO2016047683A1 (en) 2016-03-31

Family

ID=55581206

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2015/076918 WO2016047683A1 (en) 2014-09-25 2015-09-24 Medical image display processing method, medical image display processing device, and program

Country Status (6)

Country Link
US (1) US10285657B2 (en)
EP (1) EP3199102B1 (en)
JP (1) JP2016064004A (en)
CN (1) CN106659424B (en)
ES (1) ES2857099T3 (en)
WO (1) WO2016047683A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107103612A (en) * 2017-03-28 2017-08-29 深圳博脑医疗科技有限公司 Automate the quantitative calculation method of subregion brain atrophy
JP2018191722A (en) * 2017-05-12 2018-12-06 株式会社Ｓｐｌｉｎｋ Server system, and method and program executed by server system
WO2020095446A1 (en) * 2018-11-09 2020-05-14 株式会社Ｓｐｌｉｎｋ Server system, and method and program to be implemented by server system

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017075077A1 (en) * 2015-10-26 2017-05-04 The Johns Hopkins University Automated generation of sentence-based descriptors from imaging data
KR101944536B1 (en) * 2016-12-11 2019-02-01 주식회사 딥바이오 System and method for medical diagnosis using neural network
KR101754291B1 (en) * 2017-04-04 2017-07-06 이현섭 Medical image processing system and method for personalized brain disease diagnosis and status determination
EP3677181B1 (en) 2017-08-28 2021-10-13 FUJIFILM Corporation Medical image processing apparatus, medical image processing method, and medical image processing program
EP3677191B1 (en) * 2017-08-29 2023-09-20 FUJIFILM Corporation Information outputting device, method, and program
WO2019044089A1 (en) 2017-08-29 2019-03-07 富士フイルム株式会社 Medical information display device, method, and program
WO2019044095A1 (en) * 2017-08-29 2019-03-07 富士フイルム株式会社 Medical information display device, method, and program
CN108830830A (en) * 2018-05-11 2018-11-16 深圳博脑医疗科技有限公司 A kind of quantitative detecting method of brain atrophy, detection device and terminal device
JPWO2020218460A1 (en) * 2019-04-26 2020-10-29
JP7325310B2 (en) * 2019-11-28 2023-08-14 富士フイルムヘルスケア株式会社 Medical image processing device, medical image analysis device, and standard image creation program
CN111134677B (en) * 2020-02-14 2021-05-04 北京航空航天大学 Magnetic resonance image-based stroke-induced disability prediction method and system
US11694806B2 (en) * 2021-11-19 2023-07-04 Omniscient Neurotechnology Pty Limited Systems and methods for grouping brain parcellation data

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4025823B2 (en) * 2004-02-24 2007-12-26 国立精神・神経センター総長 Diagnosis support method and apparatus for brain disease
WO2012032940A1 (en) * 2010-09-07 2012-03-15 株式会社 日立メディコ Dementia diagnosis support device and dementia diagnosis support method
JP2013066632A (en) * 2011-09-26 2013-04-18 Dainippon Printing Co Ltd Medical image processing device, medical image processing method, and program
JP2014042684A (en) * 2012-08-28 2014-03-13 Dainippon Printing Co Ltd Medical image processing device, and program

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007114238A1 (en) * 2006-03-30 2007-10-11 National University Corporation Shizuoka University Apparatus for determining brain atrophy, method of determining brain atrophy and program for determining brain atrophy
JP5107538B2 (en) * 2006-07-21 2012-12-26 富士フイルムＲｉファーマ株式会社 Diagnostic imaging support system and method
WO2008073842A1 (en) * 2006-12-08 2008-06-19 Molecular Image Inc. Methods for diagnosis and monitoring of neurologic diseases using magnetic resonance methods
AU2008211786B2 (en) * 2007-01-30 2014-07-03 Ge Healthcare Limited Tools for aiding in the diagnosis of neurodegenerative diseases
WO2011040473A1 (en) * 2009-09-29 2011-04-07 大日本印刷株式会社 Method, device and program for medical image processing
CN103249358B (en) * 2010-12-02 2015-09-09 大日本印刷株式会社 Medical image-processing apparatus
JP5641629B1 (en) * 2013-10-31 2014-12-17 株式会社アラヤ・ブレイン・イメージング Personal characteristic prediction system, personal characteristic prediction method and program

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4025823B2 (en) * 2004-02-24 2007-12-26 国立精神・神経センター総長 Diagnosis support method and apparatus for brain disease
WO2012032940A1 (en) * 2010-09-07 2012-03-15 株式会社 日立メディコ Dementia diagnosis support device and dementia diagnosis support method
JP2013066632A (en) * 2011-09-26 2013-04-18 Dainippon Printing Co Ltd Medical image processing device, medical image processing method, and program
JP2014042684A (en) * 2012-08-28 2014-03-13 Dainippon Printing Co Ltd Medical image processing device, and program

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
HIROSHI MATSUDA: "2. Ninchisho no No Gazo Shindan", GERIATRIC MEDICINE, vol. 47, no. 1, 2009, pages 29 - 33, XP009501393 *
HIROSHI MATSUDA: "MRI ni yoru No Yoseki Sokutei", EIZO JOHO MEDICAL, vol. 45, no. 6, June 2013 (2013-06-01), pages 505 - 509, XP009501394 *
HIROSHI MATSUDA: "Neuronuclear imaging in medical examination of dementia", CHIRYO TO SHINDAN, vol. 97, no. Suppl., 2009, pages 101 - 111, XP009501395 *
See also references of EP3199102A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107103612A (en) * 2017-03-28 2017-08-29 深圳博脑医疗科技有限公司 Automate the quantitative calculation method of subregion brain atrophy
WO2018176985A1 (en) * 2017-03-28 2018-10-04 深圳博脑医疗科技有限公司 Quantitative calculation method for level of brain atrophy based on automatic segmentation
JP2018191722A (en) * 2017-05-12 2018-12-06 株式会社Ｓｐｌｉｎｋ Server system, and method and program executed by server system
WO2020095446A1 (en) * 2018-11-09 2020-05-14 株式会社Ｓｐｌｉｎｋ Server system, and method and program to be implemented by server system

Also Published As

Publication number Publication date
CN106659424B (en) 2020-06-09
EP3199102A4 (en) 2018-05-23
US10285657B2 (en) 2019-05-14
EP3199102B1 (en) 2021-01-27
US20170273650A1 (en) 2017-09-28
ES2857099T3 (en) 2021-09-28
CN106659424A (en) 2017-05-10
JP2016064004A (en) 2016-04-28
EP3199102A1 (en) 2017-08-02

Similar Documents

Publication Publication Date Title
WO2016047683A1 (en) Medical image display processing method, medical image display processing device, and program
Rorden et al. Age-specific CT and MRI templates for spatial normalization
JP6036009B2 (en) Medical image processing apparatus and program
JP4025823B2 (en) Diagnosis support method and apparatus for brain disease
JP5699936B2 (en) Method, apparatus and program for operating medical image processing apparatus
US8280482B2 (en) Method and apparatus for evaluating regional changes in three-dimensional tomographic images
JP5601378B2 (en) Medical image processing device
US8170347B2 (en) ROI-based assessment of abnormality using transformation invariant features
US20060239524A1 (en) Dedicated display for processing and analyzing multi-modality cardiac data
JP2010012176A (en) Brain disease diagnosis system
JP5098393B2 (en) Region of interest determination device
CN111602173A (en) Tomographic data analysis
US20100260394A1 (en) Image analysis of brain image data
JP2006208250A (en) Area classification analysis system for image data
JP4022587B2 (en) Diagnosis support method and apparatus for brain disease
Braga et al. Investigation of the cingulate cortex in idiopathic generalized epilepsy
US8938107B2 (en) System and method for automatic segmentation of organs on MR images using a combined organ and bone atlas
JP6705528B2 (en) Medical image display processing method, medical image display processing apparatus and program
Paniagua et al. 3D of brain shape and volume after cranial vault remodeling surgery for craniosynostosis correction in infants
TW201923777A (en) Image processing apparatus, image processing method and memory medium in which the degree of freedom in setting a region of interest is enhanced
Seixas et al. Anatomical brain MRI segmentation methods: volumetric assessment of the hippocampus
Maher et al. Neuroinformatics and analysis of connectomic alterations due to cerebral microhemorrhages in geriatric mild neurotrauma: microhemorrhages in geriatric neurotrauma
JP2011115270A (en) Diagnosis support system, method and computer program
Ochoa et al. Exploring anatomical brain heterogeneity in subjects with mild cognitive impairment
Amaral-Silva et al. Medical image registration using tsallis entropy in statistical parametric mapping (SPM)

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15845121

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15504774

Country of ref document: US

REEP Request for entry into the european phase

Ref document number: 2015845121

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2015845121

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE